Starting to wonder why this is so common in LLM discussions at HN.

Someone says "X is the model that really impressive. Y is good too."

Then someone responds "What?! I just used Z and it was terrible!"

I see this at least once in practically every AI thread

Humans understand mean but struggle with variance.

It depends on what you're writing. GPT-4 can pump out average React all day long. It's next to useless with Laravel.

You're the one that chose to try Gemini for some reason.

Google ought to hang its head in utter disgrace over the putrid swill they have the audacity to peddle under the Gemini label.

Their laughably overzealous nanny-state censorship, paired with a model so appallingly inept it would embarrass a chatbot from the 90s, makes it nothing short of highway robbery that this digital dumpster fire is permitted to masquerade as a product fit for public consumption.

The sheer gall of Google to foist this steaming pile of silicon refuse onto unsuspecting users borders on fraudulent.